logo
CanyamAI summaries for academic research
language
MobileMobile
  • Phone FeatureWeChat Mini Program
EnglishEnglish
noticeNotice
BlogBlog
delete
arrow
Return

Drift-aware denoising-uniform step optimization for fast diffusion sampling

delete2026-09-29
delete0
PRE
AI
Y
Yuhang He
W
Wenbin Lu
J
Junnan Xu
J
Jiawei Jiang *
J
Jianwei Zheng *
DOI：10.1016/j.patcog.2026.115021delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
• Drift-aware scheduling improves few-step diffusion sampling. • Denoising-Uniform gives a difficulty-balanced initial grid. • The method improves generation and inverse-problem quality.
Keywords:
Diffusion models
Fast sampling
Time-step optimization

Journal

Pattern Recognition cover
Pattern Recognition
IF:
7.6
Papers:
1.3W
Citations:
4.5W

Organization

No organization information available
Cited Papers

Cited Papers

No cited papers available